Elevator system management utilizing machine learning

Abstract

Systems and methods for operating an elevator system are provided. Aspects includes receiving, by a processor, a call request for an elevator car in an elevator system. Receiving sensor data from a plurality of sensors associated with the elevator car, wherein the plurality of sensors are configured to collect sensor data from one or more predefined areas associated with the elevator car. Determining an occupancy level in the elevator car based on a feature vector, generated by a machine learning model, comprising a plurality of features extracted from the sensor data and operating, by the processor, the elevator car based at least in part on the occupancy level.

What is claimed is: 
     
       1. An elevator system comprising:
 an elevator car; 
 a plurality of sensors associated with the elevator car, wherein the plurality of sensors are configured to collect sensor data from one or more predefined areas associated with the elevator car; and 
 a controller coupled to a memory, the controller configured to:
 receive a call request for the elevator car; 
 receive sensor data from the plurality of sensors; 
 
 determine an occupancy level in the elevator car based on a feature vector, generated by a machine learning model, comprising a plurality of features extracted from the sensor data; an 
 operate the elevator car based at least in part on the occupancy level in the elevator car ( 304 ); 
 wherein at least one of the one or more predefined floor areas comprises an area adjacent to an entryway for the elevator car; 
 wherein the controller is further configured to analyze, utilizing the machine learning model, the sensor data to determine a lobby occupancy level of an elevator lobby associated with the call request; 
 generate an occupancy threshold based at least in part on the lobby occupancy level; and 
 based on a determination that the occupancy level in the elevator car is above the occupancy threshold, declining the call request for the elevator car. 
 
     
     
       2. The elevator system of  claim 1 , wherein the call request is received from a hall call device receiving a user input. 
     
     
       3. The elevator system of  claim 1 , wherein the call request is received from a user device. 
     
     
       4. The elevator system of  claim 1 , wherein the controller is further configured to:
 based on a determination that the occupancy level in the elevator car is below the occupancy threshold, servicing the call request for the elevator car. 
 
     
     
       5. The elevator system of  claim 1 , wherein the plurality of sensors comprises at least one of a weight sensor and a camera. 
     
     
       6. A method for operating an elevator system, the method comprising:
 receiving, by a processor, a call request for an elevator car in an elevator system; 
 receiving sensor data from a plurality of sensors associated with the elevator car, wherein the plurality of sensors are configured to collect sensor data from one or more predefined areas associated with the elevator car), wherein at least one of the one or more predefined floor areas comprises an area adjacent to an entryway for the elevator car; 
 determining an occupancy level in the elevator car based on a feature vector, generated by a machine learning model, comprising a plurality of features extracted from the sensor data; analyzing, utilizing the machine learning model, the sensor data to determine a lobby occupancy level of an elevator lobby associated with the call request; generating an occupancy threshold based at least in part on the lobby occupancy level; 
 operating, by the processor, the elevator car based at least in part on the occupancy level in the elevator car, the operating comprising based on a determination that the occupancy level in the elevator car is above the occupancy threshold, declining the call request for the elevator car. 
 
     
     
       7. The method of  claim 6 , wherein the call request is received from a hall call device receiving a user input. 
     
     
       8. The method of  claim 6 , wherein the call request is received from a user device. 
     
     
       9. The method of  claim 6 , further comprising:
 based on a determination that the occupancy level in the elevator car is below the occupancy threshold, servicing the call request for the elevator car. 
 
     
     
       10. The method of  claim 6 , wherein the plurality of sensors comprises at least one of a weight sensor and a camera.